diff --git a/vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py b/vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py
index 8786e91a5a..f465fcad92 100644
--- a/vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py
+++ b/vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py
@@ -835,8 +835,12 @@ class LMCacheMPConnectorUpstream(KVConnectorBase_V1):
         if new_block_ids:
             tracker.append_block_ids(new_block_ids)
 
-        # Update the state of the tracker
-        condition = tracker.needs_retrieve()
+        # num_external_tokens > 0 means this connector is chosen for loading.
+        # When non-chosen (num_external_tokens == 0, e.g. in MultiConnector),
+        # force condition=False so the state goes to READY and all lookup locks
+        # are released — end_session does NOT release lookup locks, so without
+        # this they would leak until TTL expiry (10 minutes).
+        condition = tracker.needs_retrieve() and num_external_tokens > 0
         if tracker.state == LMCacheMPRequestState.PREFETCHING:
             # If need to retrieve, change to WAITING_FOR_LOAD
             # Otherwise, change to READY